[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121504-en":3,"doc-seo-121504-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},121504,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Advancing NFL win prediction - from Pythagorean formulas to machine learning algorithms","Study evaluates traditional and machine learning models for forecasting NFL team winning percentages using a 21-season dataset spanning 2003–2023. The work compares the Pythagorean expectation formula with Random Forest regression and a feedforward Neural Network, using performance indicators including points scored, points allowed, turnovers, rushing/passing efficiency, and penalties. Machine learning achieves higher predictive accuracy than the Pythagorean method, with the Neural Network yielding the strongest metrics. SHAP analysis highlights points scored and points allowed as key drivers, supplemented by margin of victory, turnovers, and offensive efficiency.","TYPE Brief Research Report PUBLISHED 12 September 2025 DOI 10.3389/fspor.2025.1638446  \nEDITED BY  \nSehwan Kim,  \nGraceland University, United States  \nREVIEWED BY  \nIgor Costa,  \nIFPB, Brazil Farjana Akter Boby,  \nDaffodil International University, Bangladesh  \n*CORRESPONDENCE  \nJun Woo Kim  \n [kimjw@arcadia.edu](kimjw@arcadia.edu)  \nRECEIVED 30 May 2025  \nACCEPTED 28 August 2025  \nPUBLISHED 12 September 2025  \nCITATION  \nWeirich C, Kim JW, Yoon Y and Jeong S (2025) Advancing NFL win prediction: from Pythagorean formulas to machine learning algorithms.  \nFront. Sports Act. Living 7:1638446 .  \ndoi: 10.3389/fspor.2025.1638446  \nCOPYRIGHT  \n© 2025 Weirich, Kim, Yoon and Jeong. This isan open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nAdvancing NFL win prediction: from Pythagorean formulas to machine learning algorithms  \nCaroline Weirich1, Jun Woo Kim1*, Youngmin Yoon2 and Seunghoon Jeong3  \n1School of Global Business, Arcadia University, Glenside, PA, United States, 2College of Education, University of North Texas, Denton, TX, United States, 3College of Physical Education, Woosuk University, Wanju-gun, Republic of Korea  \nThis study evaluates the predictive performance of traditional and machine learning-based models in forecasting NFL team winning percentages over a 21-season dataset (2003–2023) . Specifically, we compare the Pythagorean expectation formula—commonly used in sports analytics—with Random Forest regression and a feedforward Neural Network model. Using key performance indicators such as points scored, points allowed, turnovers, rushing and passing efficiency, and penalties, the machine learning models demonstrate superior predictive accuracy. The Neural Network model achieved the highest performance (MAE = 0. 052, RMSE = 0. 064, R 2 = 0. 891), followed by the Random Forest model, both of which significantly outperformed the Pythagorean method. Feature importance analysis using SHAP values identifies points scored and points allowed as the most influential predictors, supplemented by margin of victory, turnovers, and offensive efficiency metrics. These findings underscore the limitations of fixed-formula models and highlight the flexibility and robustness of datadriven approaches. The study offers practical implications for analysts, coaches, and sports management professionals seeking to optimize strategic decisions and competitive performance. Ultimately, the integration of advanced machine learning models provides a powerful tool for enhancing decision-making processes across the NFL landscape.  \nKEYWORDS  \nNFL, neural network, Pythagorean Theorem, machine learning, sports analytics, random forest  \n1 Introduction  \nAmerican football remains one of the most popular sports in the United States, consistently holding this position since 1972. The National Football League (NFL), atthe heart of this popularity, has grown into an exceptionally lucrative industry. In 2024, the combined value of the NFL’s 32 teams reached approximately $190 billion, reflecting continued financial growth and robust market presence ( 1) . Additionally, NFL viewership continues to set unprecedented records, with the 2023 playoffs averaging 38.5 million viewers, marking a notable nine-percent increase over the previous year (2) .  \nIn professional sports, success is fundamentally measured by a team’s ability to win games, and NFL explicitly employs winning percentages to determine playoff eligibility and team standings. Winning percentage is traditionally calculated by dividing a  \nFrontiers in Sports and Active Living 01 [frontiersin.org](frontiersin.or","cbCaibJK9qWTTqni","https://ap.wps.com/l/cbCaibJK9qWTTqni","pdf",974082,1,"English","en",105,"# Introduction\n## NFL winning percentage and traditional forecasting\n## Pythagorean theorem adaptations for NFL\n# Methods and models\n## Machine learning models compared\n## Performance indicators used\n## Model evaluation metrics","[{\"question\":\"What models are compared for predicting NFL team winning percentages?\",\"answer\":\"The study compares the Pythagorean expectation formula with Random Forest regression and a feedforward Neural Network over the 2003–2023 seasons.\"},{\"question\":\"Which performance metrics does the study use to build and evaluate predictions?\",\"answer\":\"Key inputs include points scored, points allowed, turnovers, rushing and passing efficiency, and penalties, and performance is reported with metrics such as MAE, RMSE, and R².\"},{\"question\":\"What do SHAP feature importance results indicate as the most influential predictors?\",\"answer\":\"SHAP identifies points scored and points allowed as the most influential predictors, with additional support from margin of victory, turnovers, and offensive efficiency metrics.\"}]","Advancing NFL win prediction - from Pythagorean formulas to machine learning algorithms | PDF",1785735984,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"advancing-nfl-win-prediction-from-pythagorean-formulas-to-machine-learning-algorithms","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/advancing-nfl-win-prediction-from-pythagorean-formulas-to-machine-learning-algorithms/121504/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What models are compared for predicting NFL team winning percentages?","Question",{"text":74,"@type":75},"The study compares the Pythagorean expectation formula with Random Forest regression and a feedforward Neural Network over the 2003–2023 seasons.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which performance metrics does the study use to build and evaluate predictions?",{"text":79,"@type":75},"Key inputs include points scored, points allowed, turnovers, rushing and passing efficiency, and penalties, and performance is reported with metrics such as MAE, RMSE, and R².",{"name":81,"@type":72,"acceptedAnswer":82},"What do SHAP feature importance results indicate as the most influential predictors?",{"text":83,"@type":75},"SHAP identifies points scored and points allowed as the most influential predictors, with additional support from margin of victory, turnovers, and offensive efficiency metrics.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]